Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 37 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3101. Min Range: -1.3101

Max Act: 1.3101. Min Act: -0.0000

Data Index: 1094582 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 1.3101. Min Range: -1.3101

Max Act: 1.2401. Min Act: -0.0000

Data Index: 1124367 (C4 (Web Text))

Max Activating Token Index: 896

Text #2

Max Range: 1.3101. Min Range: -1.3101

Max Act: 1.1418. Min Act: -0.0000

Data Index: 1161968 (C4 (Web Text))

Max Activating Token Index: 610

Text #3

Max Range: 1.3101. Min Range: -1.3101

Max Act: 1.0445. Min Act: -0.0000

Data Index: 371702 (C4 (Web Text))

Max Activating Token Index: 188

Text #4

Max Range: 1.3101. Min Range: -1.3101

Max Act: 1.0916. Min Act: -0.0000

Data Index: 126807 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 1.3101. Min Range: -1.3101

Max Act: 1.0340. Min Act: -0.0000

Data Index: 944655 (C4 (Web Text))

Max Activating Token Index: 911

Text #6

Max Range: 1.3101. Min Range: -1.3101

Max Act: 1.1316. Min Act: -0.0000

Data Index: 922784 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 1.3101. Min Range: -1.3101

Max Act: 0.9281. Min Act: -0.0000

Data Index: 841186 (C4 (Web Text))

Max Activating Token Index: 636

Text #8

Max Range: 1.3101. Min Range: -1.3101

Max Act: 0.9379. Min Act: -0.0000

Data Index: 596406 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 1.3101. Min Range: -1.3101

Max Act: 0.9577. Min Act: -0.0000

Data Index: 593451 (C4 (Web Text))

Max Activating Token Index: 492

Text #10

Max Range: 1.3101. Min Range: -1.3101

Max Act: 0.9514. Min Act: 0.0000

Data Index: 725356 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 1.3101. Min Range: -1.3101

Max Act: 0.9222. Min Act: -0.0000

Data Index: 1117562 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 1.3101. Min Range: -1.3101

Max Act: 0.8248. Min Act: -0.0000

Data Index: 1069236 (C4 (Web Text))

Max Activating Token Index: 921

Text #13

Max Range: 1.3101. Min Range: -1.3101

Max Act: 0.8425. Min Act: -0.0000

Data Index: 979270 (C4 (Web Text))

Max Activating Token Index: 739

Text #14

Max Range: 1.3101. Min Range: -1.3101

Max Act: 0.8415. Min Act: -0.0000

Data Index: 327709 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 1.3101. Min Range: -1.3101

Max Act: 0.8589. Min Act: -0.0000

Data Index: 807784 (C4 (Web Text))

Max Activating Token Index: 322

Text #16

Max Range: 1.3101. Min Range: -1.3101

Max Act: 0.8412. Min Act: 0.0001

Data Index: 321629 (C4 (Web Text))

Max Activating Token Index: 212

Text #17

Max Range: 1.3101. Min Range: -1.3101

Max Act: 0.7922. Min Act: -0.0000

Data Index: 16826 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 1.3101. Min Range: -1.3101

Max Act: 0.8654. Min Act: 0.0000

Data Index: 1169888 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 1.3101. Min Range: -1.3101

Max Act: 0.8346. Min Act: -0.0000

Data Index: 740760 (C4 (Web Text))

Max Activating Token Index: 49